© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16924
    Prev
    Next
    INDEX
    Explanations

    .com links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Б
    0.31
    ić
    0.29
    М
    0.27
    ِ
    0.27
    Д
    0.27
    З
    0.27
    Ү
    0.27
    С
    0.27
    У
    0.27
    Г
    0.26
    POSITIVE LOGITS
     pro
    0.22
     પગ
    0.22
     skilful
    0.22
    ညီ
    0.22
     functioned
    0.21
     предметы
    0.21
     ಬಾ
    0.21
     loaned
    0.20
     shoving
    0.20
     workman
    0.20
    Activations Density 0.013%

    No Known Activations